Skip to main content
Figure 4 | EURASIP Journal on Advances in Signal Processing

Figure 4

From: Classification of hyperspectral imagery with neural networks: comparison to conventional tools

Figure 4

Mean spectra of training samples and mean of the pixels classified by the SOM-hybrid ANN. The mean spectra of the training samples (solid lines) for each class and the mean of the pixels classified by the SOM-hybrid ANN into the respective classes (dashed lines), using the full, 194-band image cube. The vertical bars show the 1 standard deviation of the training samples. The mean of the predicted classes is well within this standard deviation for almost all classes. For many - such as the clay-rich series on the right - the training and class means are virtually indistinguishable (and therefore the dashed line of the class mean may not be easy to see), indicating a good match between the known training representatives and the predicted members of the classes. The bare line segments centered at 1.4 and 1.9 μ m indicate data fallout regions in the atmospheric water vapor windows.

Back to article page